ClawHub
Back to skill

Security audit

Minimum Viable Product

Security checks for vulnerabilities and agentic risk

Overview

This is a product-strategy coaching skill about designing MVP experiments, with no executable code or hidden system access.

Install this if you want structured MVP coaching. Be aware it may activate during broad product-scoping discussions and may recommend disposable experiments, so use judgment before discarding real work, taking payments, or running customer-facing tests.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest starts with specific phrases like 'MVP' and 'minimum viable product', but also adds broad situational conditions such as 'a team is scoping a build and hasn't named the assumption they're testing' and 'engineers are about to build for months on an unvalidated idea'. These are not precise trigger phrases and could match many ordinary product discussions, making invocation boundaries unclear despite the partial 'Do NOT activate' guidance.

Static analysis

No suspicious patterns detected.